Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instructions or recommendations about proper conduct

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express guidelines or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Laughs
    -0.69
    hole
    -0.67
    holes
    -0.64
     fate
    -0.64
    Fra
    -0.63
    Anyway
    -0.63
    Huh
    -0.63
    LP
    -0.62
    Sorry
    -0.60
    soDeliveryDate
    -0.59
    POSITIVE LOGITS
     adhere
    1.07
     strive
    1.06
     preferably
    1.05
     ensure
    1.04
     ideally
    1.03
     consult
    1.01
     refrain
    0.94
     beware
    0.94
     incorporate
    0.92
     avoid
    0.91
    Act Density 0.158%

    No Known Activations